Environmental safety comprehensive supervision platform based on medical disinfection area

Abstract

The invention discloses an environment safety comprehensive supervision platform based on a medical disinfection area, and relates to the technical field of medical health care information, and the platform comprises the steps: carrying out the analysis of data through a self-adaptive disinfection regulation and control algorithm carried by an algorithm module, and determining the parameters of disinfection operation; executing a disinfection operation according to the determined parameters, packaging the environmental data and the disinfection operation record into a data block by adopting encrypted hash and a distributed consensus mechanism, and storing the data block in a block chain; and dynamically grading the regional environment risk according to a preset standard, comparing the disinfected real-time monitoring data with a preset target value, and correcting the parameters of the adaptive disinfection regulation and control algorithm according to a comparison result. The invention provides a comprehensive supervision platform integrating multi-source data fusion, dynamic weight optimization, nonlinear risk assessment, closed-loop feedback control and security data storage.

Description

Technical Field

[0001] The present invention relates to the field of medical care information technology, and in particular to a comprehensive supervision platform based on environmental safety of medical disinfection areas. Background Art

[0002] The current medical disinfection field generally relies on manual monitoring and traditional timed disinfection methods. Environmental data collection is scattered and single, and there is a lack of effective fusion between sensor data. Environmental risk assessment methods are mostly based on static threshold settings, and there is a lack of real-time closed-loop control between disinfection operations and environmental monitoring. This leads to information asymmetry, delayed response, and data untraceability in safety supervision and operational control of the disinfection area. Summary of the invention

[0003] In view of the above existing problems, the present invention is proposed.

[0004] Therefore, the present invention aims to solve the problems existing in the prior art, such as the lack of integration of multi-source environmental data collection, static risk assessment, lack of closed-loop feedback in operation control, and insufficient transparency of data records. Through multi-sensor data fusion, an adaptive disinfection control algorithm based on the combination of deep learning and reinforcement learning, dynamic risk assessment grading, closed-loop feedback control and blockchain technology, data cannot be tampered with and storage is achieved. A comprehensive supervision system covering environmental monitoring, risk assessment, operation scheduling and data management is established, thereby realizing dynamic adjustment and efficient scheduling of disinfection operation parameters.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions, based on the comprehensive supervision platform of medical disinfection area environmental safety, including: In the medical disinfection area, multi-dimensional environmental data is collected through sensor modules, and the multi-dimensional environmental data is pre-processed, and data fusion technology is used to uniformly eliminate noise and redundancy; The adaptive disinfection control algorithm carried by the algorithm module is used to analyze the pre-processed multi-dimensional environmental data to determine the parameters of the disinfection operation, including disinfectant concentration, operation path and operation duration; Perform disinfection operations according to determined parameters, and collect multi-dimensional environmental data after disinfection in real time. At the same time, the multi-dimensional environmental data and disinfection operation records are encapsulated into data blocks using encrypted hashing and distributed consensus mechanisms, and stored in the blockchain; The comprehensive risk index is calculated based on the fusion algorithm carried by the algorithm module according to the multi-dimensional environmental data, and the regional environmental risks are dynamically graded according to the preset standards. At the same time, the real-time monitoring data after disinfection is compared with the preset target value, and the parameters of the adaptive disinfection control algorithm are corrected according to the comparison results. When the monitoring data exceeds the preset safety threshold, the current disinfection operation is automatically interrupted, and the automatic restart operation is implemented through step-by-step detection after the multi-dimensional environmental data returns to the safe range.

[0006] As a preferred solution of the comprehensive supervision platform for environmental safety in medical disinfection areas described in the present invention, the data fusion technology includes applying filtering algorithms to the original data of temperature and humidity data, air quality data, microbial concentration data and chemical residue data to remove random noise in the data, and using a normalization method to convert the data into a unified numerical range for different dimensions and numerical ranges of each sensor data, and extracting key feature information from the normalized data through principal component analysis and discrete wavelet transform technology, and fusing the multi-dimensional environmental data according to a predetermined data format to form a unified standard data stream; Key feature information includes temperature and humidity data, time series features, frequency domain features, correlation features, and discrete features.

[0007] As a preferred solution of the comprehensive supervision platform for environmental safety of medical disinfection areas described in the present invention, the analysis of the pre-processed multi-dimensional environmental data includes, in order to achieve weighted fusion of multi-modal data, first defining the attention weight as: ; in, Indicates The attention weight of sensor data, Indicates Sensor data The corresponding weight vector, express The transpose of represents the exponential function, Represents the total number of sensors, Represents the dimension of each sensor data, represents the jth sensor data; express The transpose of The above attention weights are used to perform weighted summation on the data of each sensor to obtain the fused data representation: ; in, Represents the fused data vector; The fused data is input by the parameter The deep neural network controlled by the algorithm obtains the hidden layer feature representation: ; in, represents the hidden layer feature vector, represents a deep neural network, represents the parameters of the deep neural network, Represents the dimension of the hidden layer vector; Based on the hidden layer representation, the strategy network is used to generate the initial control parameters: ; in, represents the initial control parameters, represents the policy network, represents the parameters of the policy network, represents the dimension of the control parameter; At the same time, the supervision module is used to represent the hidden layer Generate auxiliary control parameters: ; in, represents auxiliary control parameters, represents the supervision module, Represents the parameters of the supervision module.

[0008] As a preferred solution of the comprehensive supervision platform for environmental safety of medical disinfection areas described in the present invention, the analysis of the pre-processed multi-dimensional environmental data also includes introducing an adaptive weight factor to achieve dynamic fusion of preliminary and auxiliary parameters, which is defined as: ; in, represents the adaptive fusion weight, represents the Sigmoid function, represents the vector used to calculate the weights, represents the bias term; The initial control parameters and auxiliary control parameters are fused according to the adaptive weight factor to obtain the preliminary control parameters: ; in, represents preliminary control parameters; In order to correct the uncertainty of the preliminary control parameters, the Bayesian layer is introduced to model the posterior distribution of the hidden layer features, and the uncertainty correction formula is defined: ; in, represents the final control parameter, represents the uncertainty adjustment constant, Represents the Bayesian posterior distribution The standard deviation vector extracted from , i.e., the uncertainty measure.

[0009] As a preferred solution of the comprehensive supervision platform for environmental safety in medical disinfection areas described in the present invention, the analysis of the pre-processed multi-dimensional environmental data also includes introducing a reinforcement learning module to achieve strategy evaluation based on time difference, and its time difference target is defined as: ; in, represents the time difference target, Represents the reward function value corresponding to the state and action, Indicates the current state. represents the discount factor, represents the candidate actions for the next moment, represents the hidden feature vector generated by the deep network at the next moment, Indicated by the parameter Determined Q-value function; Finally, a multi-objective loss function is constructed to jointly train the entire model, which is defined as: ; in, represents the total loss function, Indicates the generation of the final control parameters With reference parameters The error measurement function between represents the reference control parameter, represents the weight factor of the reinforcement learning error term, represents the weight factor of the uncertainty regularization term, Represents the square of the L2 norm of the uncertainty vector.

[0010] As a preferred solution of the medical disinfection area environmental safety integrated supervision platform described in the present invention, the encapsulation into data blocks using encrypted hashing and distributed consensus mechanism includes defining a single data record: ; in, Indicates A data record containing multi-dimensional environmental data collected by an environmental sensor , ,in Environmental data dimension, operation records collected by disinfection equipment ,in Record dimensions for the operation, as well as the timestamp of the record ; Generate a data digest, i.e. a hash value: ; in, Indicates The hash value of each data record, represents a cryptographic hash function, symbol Represents a serial operation, Expressed as A random salt generated for each data record, Indicates the hash value of the previous block, and defines the initial value for the first block ; Encapsulate data records into data blocks: ; in, Indicates data blocks, Indicates the timestamp of when the data block was generated. For the A set of valid digital signatures obtained for a data block.

[0011] As a preferred solution of the comprehensive supervision platform for environmental safety of medical disinfection areas described in the present invention, the encapsulation into data blocks using encrypted hashing and distributed consensus mechanisms also includes defining a valid digital signature set generated by each supervision node in the distributed consensus: ; in, Indicates the supervisory node , for data blocks The generated digital signature, is the set of regulatory nodes participating in the consensus. is the indicator function, when the node The generated digital signature takes the value 1 if it passes verification, otherwise it takes the value 0; Introduce a dynamic consensus threshold to determine whether a block consensus is reached: ; in, Indicates the minimum number of valid signatures required for consensus, Represents a dynamic adjustment parameter, whose value range is And used to adjust the strictness of consensus, Indicates the total number of regulatory nodes participating in the consensus, symbol Represents the ceiling function.

[0012] As a preferred solution of the comprehensive supervision platform for environmental safety of medical disinfection areas described in the present invention, the encapsulation into data blocks using encrypted hashing and distributed consensus mechanism also includes determining the conditions for reaching consensus on the blocks: ; in, Representing a collection The number of valid digital signatures in the consensus threshold. When, block It is considered to have passed consensus and can be stored synchronously among various regulatory nodes; Constructing a complete blockchain structure: ; in, Indicated by The blockchain structure consists of data blocks. The total number of data blocks.

[0013] As a preferred solution of the comprehensive supervision platform for environmental safety in medical disinfection areas described in the present invention, the comprehensive risk index calculated by the fusion algorithm includes: , air quality data , Microbial concentration data and chemical residue data The normalized data were processed by the minimum-maximum normalization method. and ; Using the dynamic weight optimization module based on genetic algorithm, the initial weight and As input, through the weight adjustment function Output updated weights and ; Using the weighted fusion formula: ;

[0014] Calculate the comprehensive risk index ; Use fuzzy logic control method to construct risk assessment function , and set the preset risk threshold sequence , where each value in the sequence Represents the risk cutoff point and adopts the Bayesian update mechanism to use the prior distribution The likelihood function corresponding to the observed data Using the update formula: ;

[0015] Dynamically adjust the threshold sequence to Divided into discrete risk levels ,in Represents the oth level risk category; this discrete risk level serves as input data for the dynamic adjustment module of disinfection operation parameters in subsequent steps; represents the posterior distribution.

[0016] As a preferred solution of the comprehensive supervision platform for environmental safety of medical disinfection areas described in the present invention, the parameters of the adaptive disinfection control algorithm modified according to the comparison results include: after the disinfection operation is completed, the system collects the post-disinfection environmental data in real time through the environmental sensor, which is recorded as , and With the preset target environment data Compare and calculate the error signal , which is defined as: ; in, represents the error signal, i.e., the difference between the target value and the actual measured value; The error signal Input to the feedback control module, which uses the proportional-integral-differential PID control algorithm, and its calculation formula is: ' in, represents the parameter correction amount, is the proportional gain vector, is the integral gain vector, is the differential gain vector, is the current time, is the integration variable, and Represents the dimension of the adaptive disinfection control algorithm parameters; The parameter correction amount and the current parameter Add and update to get new parameters ,Right now: ; in, is the parameter set of the current disinfection control algorithm, the new parameter It is used to update the control settings in the disinfection operation in real time, thus forming a closed-loop feedback system to achieve continuous automatic adjustment of disinfection operation parameters.

[0017] Beneficial effects of the invention: The invention provides a comprehensive supervision platform that integrates multi-source data fusion, dynamic weight optimization, nonlinear risk assessment, closed-loop feedback control and secure data storage, so that the disinfection operation can automatically adjust the operating parameters according to the real-time environmental monitoring data, ensuring the real-time correspondence between the monitoring information and the disinfection execution, improving the scientificity and transparency of the medical disinfection area management, and realizing the full recording and traceability of the data, providing an efficient and intelligent comprehensive supervision technology solution for the medical environment safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0019] Figure 1 A schematic diagram of the process flow of a comprehensive supervision platform for environmental safety in medical disinfection areas provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0024] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0025] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0026] Example 1, reference Figure 1 , which is the first embodiment of the present invention, provides a comprehensive supervision platform based on environmental safety of medical disinfection areas, including: S1: In the medical disinfection area, multi-dimensional environmental data is collected through sensor modules, and the multi-dimensional environmental data is pre-processed, and data fusion technology is used to uniformly eliminate noise and redundancy.

[0027] The data fusion technology includes applying filtering algorithms to the original data of temperature and humidity data, air quality data, microbial concentration data and chemical residue data to remove random noise in the data, using a normalization method to convert the data into a unified numerical range for different dimensions and numerical ranges of each sensor data, and extracting key feature information from the normalized data through principal component analysis and discrete wavelet transform technology, and fusing the multi-dimensional environmental data according to a predetermined data format to form a unified standard data stream; Key feature information includes temperature and humidity data, time series features, frequency domain features, correlation features, and discrete features.

[0028] S2: Use the adaptive disinfection control algorithm carried by the algorithm module to analyze the pre-processed multi-dimensional environmental data and determine the parameters of the disinfection operation, including disinfectant concentration, operation path and operation duration.

[0029] The analysis of the pre-processed multi-dimensional environmental data includes, in order to achieve weighted fusion of multi-modal data, first defining the attention weight as: ; in, Indicates The attention weight of sensor data, Indicates Sensor data The corresponding weight vector, express The transpose of represents the exponential function, Represents the total number of sensors, Represents the dimension of each sensor data, represents the jth sensor data; express The transpose of The above attention weights are used to perform weighted summation on the data of each sensor to obtain the fused data representation: ; in, Represents the fused data vector; The fused data is input by the parameter The deep neural network controlled by the algorithm obtains the hidden layer feature representation: ; in, represents the hidden layer feature vector, represents a deep neural network, represents the parameters of the deep neural network, Represents the dimension of the hidden layer vector; Based on the hidden layer representation, the strategy network is used to generate the initial control parameters:

[0030] in, represents the initial control parameters, represents the policy network, represents the parameters of the policy network, represents the dimension of the control parameter; At the same time, the supervision module is used to represent the hidden layer Generate auxiliary control parameters: ; in, represents auxiliary control parameters, represents the supervision module, Represents the parameters of the supervision module.

[0031] The analysis of the pre-processed multi-dimensional environmental data also includes introducing an adaptive weight factor to achieve dynamic fusion of the primary and auxiliary parameters, which is defined as: ; in, represents the adaptive fusion weight, represents the Sigmoid function, represents the vector used to calculate the weights, represents the bias term; The initial control parameters and auxiliary control parameters are fused according to the adaptive weight factor to obtain the preliminary control parameters: ; in, represents preliminary control parameters; In order to correct the uncertainty of the preliminary control parameters, the Bayesian layer is introduced to model the posterior distribution of the hidden layer features, and the uncertainty correction formula is defined: ; in, represents the final control parameter, represents the uncertainty adjustment constant, Represents the Bayesian posterior distribution The standard deviation vector extracted from , i.e., the uncertainty measure.

[0032] The analysis of the pre-processed multi-dimensional environmental data also includes introducing a reinforcement learning module to achieve strategy evaluation based on time difference, and its time difference target is defined as: ; in, represents the time difference target, Represents the reward function value corresponding to the state and action, Indicates the current state. represents the discount factor, represents the candidate actions for the next moment, represents the hidden feature vector generated by the deep network at the next moment, Indicated by the parameter Determined Q-value function; Finally, a multi-objective loss function is constructed to jointly train the entire model, which is defined as: ; in, represents the total loss function, Indicates the generation of the final control parameters With reference parameters The error measurement function between represents the reference control parameter, represents the weight factor of the reinforcement learning error term, represents the weight factor of the uncertainty regularization term, Represents the square of the L2 norm of the uncertainty vector.

[0033] S3: Perform disinfection operations according to determined parameters, and collect multi-dimensional environmental data after disinfection in real time. At the same time, the multi-dimensional environmental data and disinfection operation records are encapsulated into data blocks using encrypted hashing and distributed consensus mechanisms, and stored in the blockchain.

[0034] The encapsulation into data blocks using encrypted hashing and distributed consensus mechanisms includes defining a single data record: ; in, Indicates A data record containing multi-dimensional environmental data collected by an environmental sensor , ,in Environmental data dimension, operation records collected by disinfection equipment ,in Record dimensions for the operation, as well as the timestamp of the record ; Generate a data digest, i.e. a hash value:

[0035] in, Indicates The hash value of each data record, represents a cryptographic hash function, symbol Represents a serial operation, Expressed as A random salt generated for each data record, Indicates the hash value of the previous block, and defines the initial value for the first block ; Encapsulate data records into data blocks: ; in, Indicates data blocks, Indicates the timestamp of when the data block was generated. For the A set of valid digital signatures obtained for a data block.

[0036] The encapsulation into data blocks using encrypted hashing and distributed consensus mechanisms also includes defining a set of valid digital signatures generated by each supervisory node in the distributed consensus: ; in, Indicates the supervisory node , for data blocks The generated digital signature, is the set of regulatory nodes participating in the consensus. is the indicator function, when the node The generated digital signature takes the value 1 if it passes verification, otherwise it takes the value 0; Introduce a dynamic consensus threshold to determine whether a block consensus is reached: ; in, Indicates the minimum number of valid signatures required for consensus, Represents a dynamic adjustment parameter, whose value range is And used to adjust the strictness of consensus, Indicates the total number of regulatory nodes participating in the consensus, symbol Represents the ceiling function.

[0037] The encapsulation into data blocks by using encrypted hashing and distributed consensus mechanism also includes determining the conditions for reaching block consensus: ; in, Representing a collection The number of valid digital signatures in the consensus threshold. When, block It is considered to have passed consensus and can be stored synchronously among various regulatory nodes; Constructing a complete blockchain structure: ;

[0038] in, Indicated by The blockchain structure consists of data blocks. The total number of data blocks.

[0039] The above formulas describe in sequence the entire process from the composition of a single data record, using a cryptographic hash algorithm combined with a random salt and the hash value of the previous block to generate a data summary, encapsulating it into a block, generating a digital signature between regulatory nodes, and using a dynamic consensus threshold to determine the block consensus, until a complete blockchain is formed. Each formula inherits the result of the previous formula and explains each symbol in detail.

[0040] S4: The comprehensive risk index is calculated based on the fusion algorithm carried by the algorithm module according to the multi-dimensional environmental data, and the regional environmental risks are dynamically graded according to the preset standards. At the same time, the real-time monitoring data after disinfection is compared with the preset target value, and the parameters of the adaptive disinfection control algorithm are corrected according to the comparison results. When the monitoring data exceeds the preset safety threshold, the current disinfection operation is automatically interrupted, and the automatic restart operation is implemented through step-by-step detection after the multi-dimensional environmental data returns to the safe range.

[0041] The fusion algorithm used to calculate the comprehensive risk index includes: (temperature and relative humidity values ​​collected by temperature and humidity sensors), air quality data (PM2.5 concentration, PM10 concentration, carbon dioxide concentration and volatile organic compound concentration collected by air quality sensors), microbial concentration data (Bacteria concentration, virus concentration and fungus concentration collected by microbiological detector) and chemical residue data The residual concentration of disinfectant and other chemical substances collected by the chemical residue detection sensor were processed by the minimum-maximum normalization method to obtain normalized data. and ; Using the dynamic weight optimization module based on genetic algorithm, the initial weight and As input, through the weight adjustment function Output updated weights and (in : is the trained weight optimization function); using the weighted fusion formula: ;

[0042] Calculate the comprehensive risk index (in represents the fused environmental risk value); constructs the risk assessment function using fuzzy logic control method (in The continuous value Mapped to a discrete risk level set, and the mapping process uses a local weighted regression method to ensure the smoothness of the mapping function), while setting a preset risk threshold sequence (where each value in the sequence represents the risk cutoff point) and adopts the Bayesian update mechanism to The likelihood function corresponding to the observed data Using the update formula ;

[0043] Dynamically adjust the threshold sequence to Divided into discrete risk levels (in represents the oth level risk category); this discrete risk level is used as the input data of the dynamic adjustment module of disinfection operation parameters in the subsequent steps; the above process from data normalization, dynamic weight optimization, weighted fusion, nonlinear risk mapping to dynamic threshold update constitutes an environmental risk assessment technical method based on multi-dimensional environmental data fusion; represents the posterior distribution.

[0044] The parameters of the adaptive disinfection control algorithm modified according to the comparison results include: after the disinfection operation is completed, the system collects the post-disinfection environmental data in real time through the environmental sensor, which is recorded as , and With the preset target environment data Compare and calculate the error signal , which is defined as: ; in, represents the error signal, i.e., the difference between the target value and the actual measured value; The error signal Input to the feedback control module, which uses the proportional-integral-differential PID control algorithm, and its calculation formula is: ; in, represents the parameter correction amount, is the proportional gain vector, is the integral gain vector, is the differential gain vector, is the current time, is the integration variable, and Represents the dimension of the adaptive disinfection control algorithm parameters; The parameter correction amount and the current parameter Add and update to get new parameters ,Right now: ; in, is the parameter set of the current disinfection control algorithm, the new parameter It is used to update the control settings in the disinfection operation in real time, thus forming a closed-loop feedback system to achieve continuous automatic adjustment of disinfection operation parameters.

[0045] Example 2 The second embodiment of the present invention is different from the previous embodiment in that: If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0046] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0050] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. Based on the comprehensive supervision platform of environmental safety in medical disinfection areas, it is characterized by: include, In the medical disinfection area, multi-dimensional environmental data is collected through sensor modules, and the multi-dimensional environmental data is pre-processed, and data fusion technology is used to uniformly eliminate noise and redundancy; The adaptive disinfection control algorithm carried by the algorithm module is used to analyze the pre-processed multi-dimensional environmental data to determine the parameters of the disinfection operation, including disinfectant concentration, operation path and operation duration; Perform disinfection operations according to determined parameters, and collect multi-dimensional environmental data after disinfection in real time. At the same time, the multi-dimensional environmental data and disinfection operation records are encapsulated into data blocks using encrypted hashing and distributed consensus mechanisms, and stored in the blockchain; The comprehensive risk index is calculated based on the fusion algorithm carried by the algorithm module according to the multi-dimensional environmental data, and the regional environmental risks are dynamically graded according to the preset standards. At the same time, the real-time monitoring data after disinfection is compared with the preset target value, and the parameters of the adaptive disinfection control algorithm are corrected according to the comparison results. When the monitoring data exceeds the preset safety threshold, the current disinfection operation is automatically interrupted, and the automatic restart operation is implemented through step-by-step detection after the multi-dimensional environmental data returns to the safe range.

2. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 1 is characterized by: The data fusion technology includes applying filtering algorithms to the original data of temperature and humidity data, air quality data, microbial concentration data and chemical residue data to remove random noise in the data, using a normalization method to convert the data into a unified numerical range for different dimensions and numerical ranges of each sensor data, and extracting key feature information from the normalized data through principal component analysis and discrete wavelet transform technology, and fusing the multi-dimensional environmental data according to a predetermined data format to form a unified standard data stream; Key feature information includes temperature and humidity data, time series features, frequency domain features, correlation features, and discrete features.

3. The comprehensive supervision platform based on medical disinfection area environmental safety as claimed in claim 2 is characterized by: The analysis of the pre-processed multi-dimensional environmental data includes, in order to achieve weighted fusion of multi-modal data, first defining the attention weight as: ； in, Indicates The attention weight of sensor data, Indicates Sensor data The corresponding weight vector, express The transpose of represents the exponential function, Indicates the total number of sensors, Represents the dimension of each sensor data, Indicates Sensor data; express The transpose of The above attention weights are used to perform weighted summation on the data of each sensor to obtain the fused data representation: ； in, Represents the fused data vector; The fused data is input by the parameter The deep neural network controlled by the algorithm obtains the hidden layer feature representation: ； in, represents the hidden layer feature vector, represents a deep neural network, represents the parameters of the deep neural network, Represents the dimension of the hidden layer vector; Based on the hidden layer representation, the strategy network is used to generate the initial control parameters: ； in, represents the initial control parameters, represents the policy network, represents the parameters of the policy network, represents the dimension of the control parameter; At the same time, the supervision module is used to represent the hidden layer Generate auxiliary control parameters: ； in, represents auxiliary control parameters, represents the supervision module, Represents the parameters of the supervision module.

4. The comprehensive supervision platform based on medical disinfection area environmental safety as claimed in claim 3 is characterized by: The analysis of the pre-processed multi-dimensional environmental data also includes introducing an adaptive weight factor to achieve dynamic fusion of the primary and auxiliary parameters, which is defined as: ； in, represents the adaptive fusion weight, represents the Sigmoid function, represents the vector used to calculate the weights, represents the bias term; The initial control parameters and auxiliary control parameters are fused according to the adaptive weight factor to obtain the preliminary control parameters: ； in, represents preliminary control parameters; In order to correct the uncertainty of the preliminary control parameters, the Bayesian layer is introduced to model the posterior distribution of the hidden layer features, and the uncertainty correction formula is defined: ； in, represents the final control parameter, represents the uncertainty adjustment constant, Represents the Bayesian posterior distribution The standard deviation vector extracted from , i.e., the uncertainty measure.

5. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 4 is characterized by: The analysis of the pre-processed multi-dimensional environmental data also includes introducing a reinforcement learning module to achieve strategy evaluation based on time difference, and its time difference target is defined as: ； in, represents the time difference target, Represents the reward function value corresponding to the state and action, Indicates the current state. represents the discount factor, represents the candidate actions for the next moment, represents the hidden feature vector generated by the deep network at the next moment, Indicated by the parameter Determined Q-value function; Finally, a multi-objective loss function is constructed to jointly train the entire model, which is defined as: ； in, represents the total loss function, Indicates the generation of the final control parameters With reference parameters The error measurement function between Indicates reference control parameters represents the weight factor of the reinforcement learning error term, represents the weight factor of the uncertainty regularization term, Represents the square of the L2 norm of the uncertainty vector.

6. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 5 is characterized by: The encapsulation into data blocks using encrypted hashing and distributed consensus mechanisms includes defining a single data record: ； in, Indicates A data record containing multi-dimensional environmental data collected by an environmental sensor , ( ),in Environmental data dimension, operation records collected by disinfection equipment ,in Record dimensions for the operation, as well as the timestamp of the record ; Generate a data digest, i.e. a hash value: ； in, Indicates The hash value of each data record, represents a cryptographic hash function, symbol Represents a serial operation, Expressed as A random salt generated for each data record, Indicates the hash value of the previous block, and defines the initial value for the first block ; Encapsulate data records into data blocks: ； in, Indicates data blocks, Indicates the timestamp of when the data block was generated. For the A set of valid digital signatures obtained for a data block.

7. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 6 is characterized by: The encapsulation into data blocks using encrypted hashing and distributed consensus mechanisms also includes defining a valid digital signature set generated by each supervisory node in the distributed consensus: ； in, Indicates the supervisory node , for data blocks The generated digital signature, is the set of regulatory nodes participating in the consensus. is the indicator function, when the node The generated digital signature takes the value 1 if it passes verification, otherwise it takes the value 0; Introduce a dynamic consensus threshold to determine whether a block consensus is reached: ； in, Indicates the minimum number of valid signatures required for consensus, Represents a dynamic adjustment parameter, whose value range is And used to adjust the strictness of consensus, Indicates the total number of regulatory nodes participating in the consensus, symbol Represents the ceiling function.

8. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 7 is characterized by: The encapsulation into data blocks by using encrypted hashing and distributed consensus mechanism also includes determining the conditions for reaching block consensus: ； in, Representing a collection The number of valid digital signatures in the consensus threshold. When, block It is considered to have passed consensus and can be stored synchronously among various regulatory nodes; Constructing a complete blockchain structure: ； in, Indicated by The blockchain structure consists of data blocks. The total number of data blocks.

9. The comprehensive supervision platform based on environmental safety of medical disinfection areas as claimed in claim 8 is characterized by: The calculation of the comprehensive risk index includes: , air quality data , Microbial concentration data and chemical residue data The normalized data were processed by the minimum-maximum normalization method. and ; Using the dynamic weight optimization module based on genetic algorithm, the initial weight and As input, through the weight adjustment function Output updated weights and ; Using the weighted fusion formula: ； Calculate the comprehensive risk index ; Constructing risk assessment function using fuzzy logic control method , and set the preset risk threshold sequence , where each value in the sequence Represents the risk cutoff point and adopts the Bayesian update mechanism to use the prior distribution The likelihood function corresponding to the observed data Using the update formula: ； Dynamically adjust the threshold sequence to Divided into discrete risk levels ,in Indicates the risk category of level o; represents the posterior distribution.

10. The comprehensive supervision platform based on medical disinfection area environmental safety as claimed in claim 9 is characterized by: The parameters of the adaptive disinfection control algorithm modified according to the comparison results include: after the disinfection operation is completed, the system collects the post-disinfection environmental data in real time through the environmental sensor, which is recorded as , and With the preset target environment data Compare and calculate the error signal , which is defined as: ； in, represents the error signal, i.e., the difference between the target value and the actual measured value; The error signal Input to the feedback control module, which uses the proportional-integral-differential PID control algorithm, and its calculation formula is: ； in, represents the parameter correction amount, is the proportional gain vector, is the integral gain vector, is the differential gain vector, is the current time, is the integration variable, and Represents the dimension of the adaptive disinfection control algorithm parameters; The parameter correction amount and the current parameter Add and update to get new parameters ,Right now: ； in, is the parameter set of the current disinfection control algorithm, the new parameter It is used to update the control settings in the disinfection operation in real time, thus forming a closed-loop feedback system to achieve continuous automatic adjustment of disinfection operation parameters.

Images